HappyZ happyz
happyz synced and deleted reference refs/tags/refs/pull/6735/merge at happyz/llama.cpp from mirror 2024-04-18 11:13:05 -07:00
happyz synced and deleted reference refs/tags/refs/pull/6646/merge at happyz/llama.cpp from mirror 2024-04-18 11:13:05 -07:00
happyz synced and deleted reference refs/tags/refs/pull/6588/merge at happyz/llama.cpp from mirror 2024-04-18 11:13:05 -07:00
happyz synced and deleted reference refs/tags/refs/pull/6508/merge at happyz/llama.cpp from mirror 2024-04-18 11:13:05 -07:00
happyz synced and deleted reference refs/tags/refs/pull/6505/merge at happyz/llama.cpp from mirror 2024-04-18 11:13:05 -07:00
happyz synced commits to gg/flash-attn at happyz/llama.cpp from mirror 2024-04-18 11:13:05 -07:00
fa9e8c6689 Merge branch 'master' into gg/flash-attn
e11b2e6e1e Qwen2 : assume tied weights if lm_head/output weights is missing (#6738)
105332cc17 metal : add BS=1 kernel for flash attention (#6508)
260cdb2d08 llama-bench : add -fa,--flash-attn arg
87968de9a9 fix KQ FP32 precision fpr parallel_blocks > 1
Compare 14 commits »
happyz synced commits to master at happyz/llama.cpp from mirror 2024-04-18 11:13:05 -07:00
0d56246f4b ggml : group all experts in a single ggml_mul_mat_id (#6505)
03c0946d73 convert : support models with multiple chat templates (#6588)
e11b2e6e1e Qwen2 : assume tied weights if lm_head/output weights is missing (#6738)
c71bfd736e llama : fix compatibility with old 2 expert models (#6735)
Compare 4 commits »
happyz synced and deleted reference refs/tags/sl/moe-extra-tensors-fix at happyz/llama.cpp from mirror 2024-04-18 11:13:04 -07:00
happyz synced and deleted reference refs/tags/gg/flash-attn-vec at happyz/llama.cpp from mirror 2024-04-18 11:13:04 -07:00
happyz synced and deleted reference refs/tags/refs/pull/6156/merge at happyz/llama.cpp from mirror 2024-04-18 11:13:04 -07:00
happyz synced and deleted reference refs/tags/sl/moe-rework-2 at happyz/llama.cpp from mirror 2024-04-18 11:13:04 -07:00
happyz synced commits to refs/pull/2323/head at happyz/Fooocus from mirror 2024-04-18 11:13:01 -07:00
a27d49bf8a Added return type to function
06726e795e Addressed PR comments
Compare 2 commits »
happyz synced commits to refs/pull/2323/merge at happyz/Fooocus from mirror 2024-04-18 11:13:01 -07:00
a27d49bf8a Added return type to function
06726e795e Addressed PR comments
Compare 3 commits »
happyz synced commits to refs/pull/10895/merge at happyz/fastapi from mirror 2024-04-18 11:12:53 -07:00
0e831f5c3d Merge branch 'master' into bugfix/responses-model-openapi
Compare 2 commits »
happyz synced commits to refs/pull/10895/head at happyz/fastapi from mirror 2024-04-18 11:12:53 -07:00
0e831f5c3d Merge branch 'master' into bugfix/responses-model-openapi
3425c834cc 📝 Update release notes
91606c3c38 🌐 Add Russian translation for `docs/ru/docs/tutorial/dependencies/dependencies-in-path-operation-decorators.md` (#11411)
7e161b3f9e 📝 Update release notes
9e074c2ed2 📝 Fix typo in `docs/es/docs/async.md` (#11400)
Compare 365 commits »
happyz synced commits to main at happyz/memos from mirror 2024-04-18 11:12:51 -07:00
e8dfd579c3 chore: update background services
2a93b8d720 chore: tweak linter
5d967f41d9 chore: update server
339fecbfff chore: allow search comments
Compare 4 commits »
happyz synced commits to refs/pull/3244/merge at happyz/memos from mirror 2024-04-18 11:12:51 -07:00
e8dfd579c3 chore: update background services
2a93b8d720 chore: tweak linter
5d967f41d9 chore: update server
339fecbfff chore: allow search comments
Compare 5 commits »
happyz synced new reference test_625738549 to happyz/gemma.cpp from mirror 2024-04-17 23:13:21 -07:00
happyz synced commits to test_625738549 at happyz/gemma.cpp from mirror 2024-04-17 23:13:21 -07:00
happyz synced new reference refs/tags/b2690 to happyz/llama.cpp from mirror 2024-04-17 23:13:18 -07:00